most common value in train

2021-07-06 10:39:57 +02:00 · 2021-07-06 10:39:57 +02:00 · 161712a7a4
commit 161712a7a4
parent c8a53ba235
3 changed files with 297453 additions and 0 deletions
--- a/dev-0/out.tsv
+++ b/dev-0/out.tsv
--- a/most_common_from_train/a.py
+++ b/most_common_from_train/a.py
@ -0,0 +1,11 @@
+import pandas as pd
+
+r_out = pd.read_csv('../train/expected.tsv', names = ('class',))
+most_common = r_out['class'].value_counts().idxmax()
+
+
+for dataset in 'dev-0', 'test-A':
+    with open(f'../{dataset}/out.tsv', 'w') as f_out, open(f'../{dataset}/in.tsv', 'r') as f_in:
+        for line_in in f_in:
+            f_out.write(most_common + '\n')
+
--- a/test-A/out.tsv
+++ b/test-A/out.tsv